3 papers
cs.LG2026
Compressed Computation under Loss is likely Computation in Superposition
Francisco Ferreira da Silva, Stefan Heimersheim
Neural networks are thought to represent concepts as directions in their activation space, and superposition lets them encode more concepts than they have dimensions. It is natural…
cs.LG2026
Evidence for feature-specific error correction in LLMs
Francisco Ferreira da Silva, Stefan Heimersheim
Understanding the features of large language models (LLMs) is a central goal of interpretability. LLMs are commonly assumed to use superposition to represent more features than the…
quant-ph2026
Entanglement improves coordination in distributed systems
Francisco Ferreira da Silva, Stephanie Wehner
Coordination in distributed systems is often hampered by communication latency, which degrades performance. Quantum entanglement offers fundamentally stronger correlations than cla…